Convolutional Neural Network Interpretability with General Pattern Theory

• URL: http://arxiv.org/abs/2102.04247v1
• Date: Fri, 5 Feb 2021 07:11:48 GMT
• Title: Convolutional Neural Network Interpretability with General Pattern Theory
• Authors: Erico Tjoa, Guan Cuntai
• Abstract summary: Improved interpretability of deep neural networks (DNNs) has practical benefits, such as more accountable usage, better algorithm maintenance and improvement. We propose to use pattern theory formulated by Ulf Grenander, in which data can be described as configurations of fundamental objects. U-Net-like structure is formed by attaching expansion blocks (EB) to ResNet, allowing it to perform semantic segmentation-like tasks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ongoing efforts to understand deep neural networks (DNN) have provided many insights, but DNNs remain incompletely understood. Improving DNN's interpretability has practical benefits, such as more accountable usage, better algorithm maintenance and improvement. The complexity of dataset structure may contribute to the difficulty in solving interpretability problem arising from DNN's black-box mechanism. Thus, we propose to use pattern theory formulated by Ulf Grenander, in which data can be described as configurations of fundamental objects that allow us to investigate convolutional neural network's (CNN) interpretability in a component-wise manner. Specifically, U-Net-like structure is formed by attaching expansion blocks (EB) to ResNet, allowing it to perform semantic segmentation-like tasks at its EB output channels designed to be compatible with pattern theory's configurations. Through these modules, some heatmap-based explainable artificial intelligence (XAI) methods will be shown to extract explanations w.r.t individual generators that make up a single data sample, potentially reducing the impact of dataset's complexity to interpretability problem. The MNIST-equivalent dataset containing pattern theory's elements is designed to facilitate smoother entry into this framework, along which the theory's generative aspect is naturally presented.

Related papers

• COMBINEX: A Unified Counterfactual Explainer for Graph Neural Networks via Node Feature and Structural Perturbations [6.894071825948456]
  We propose COMBINEX, a novel GNN explainer that generates counterfactual explanations for both node and graph classification tasks. Unlike prior methods, which treat structural and feature-based changes independently, COMBINEX optimally balances modifications to edges and node features. This unified approach ensures minimal yet effective changes required to flip a model's prediction, resulting in realistic and interpretable counterfactuals.
  arXiv  Detail & Related papers  (2025-02-14T12:17:24Z)
• Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
  We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training. It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby. It can be combined with both discriminative and generative neural models.
  arXiv  Detail & Related papers  (2024-05-12T22:18:25Z)
• Learning Invariant Representations of Graph Neural Networks via Cluster Generalization [58.68231635082891]
  Graph neural networks (GNNs) have become increasingly popular in modeling graph-structured data. In this paper, we experimentally find that the performance of GNNs drops significantly when the structure shift happens. We propose the Cluster Information Transfer (CIT) mechanism, which can learn invariant representations for GNNs.
  arXiv  Detail & Related papers  (2024-03-06T10:36:56Z)
• Factorized Explainer for Graph Neural Networks [7.382632811417645]
  Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. Post-hoc instance-level explanation methods have been proposed to understand GNN predictions. We introduce a novel factorized explanation model with theoretical performance guarantees.
  arXiv  Detail & Related papers  (2023-12-09T15:29:45Z)
• Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting [52.47493322446537]
  We develop a adaptive, interpretable and scalable forecasting framework, which seeks to individually model each component of the spatial-temporal patterns. SCNN works with a pre-defined generative process of MTS, which arithmetically characterizes the latent structure of the spatial-temporal patterns. Extensive experiments are conducted to demonstrate that SCNN can achieve superior performance over state-of-the-art models on three real-world datasets.
  arXiv  Detail & Related papers  (2023-05-22T13:39:44Z)
• Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis [94.64007376939735]
  We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training. We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
  arXiv  Detail & Related papers  (2022-05-11T17:43:54Z)
• Universal approximation property of invertible neural networks [76.95927093274392]
  Invertible neural networks (INNs) are neural network architectures with invertibility by design. Thanks to their invertibility and the tractability of Jacobian, INNs have various machine learning applications such as probabilistic modeling, generative modeling, and representation learning.
  arXiv  Detail & Related papers  (2022-04-15T10:45:26Z)
• BScNets: Block Simplicial Complex Neural Networks [79.81654213581977]
  Simplicial neural networks (SNN) have recently emerged as the newest direction in graph learning. We present Block Simplicial Complex Neural Networks (BScNets) model for link prediction. BScNets outperforms state-of-the-art models by a significant margin while maintaining low costs.
  arXiv  Detail & Related papers  (2021-12-13T17:35:54Z)
• Random Graph-Based Neuromorphic Learning with a Layer-Weaken Structure [4.477401614534202]
  We transform the random graph theory into an NN model with practical meaning and based on clarifying the input-output relationship of each neuron. Under the usage of this low-operation cost approach, neurons are assigned to several groups of which connection relationships can be regarded as uniform representations of random graphs they belong to. We develop a joint classification mechanism involving information interaction between multiple RGNNs and realize significant performance improvements in supervised learning for three benchmark tasks.
  arXiv  Detail & Related papers  (2021-11-17T03:37:06Z)
• Investigating the Compositional Structure Of Deep Neural Networks [1.8899300124593645]
  We introduce a novel theoretical framework based on the compositional structure of piecewise linear activation functions. It is possible to characterize the instances of the input data with respect to both the predicted label and the specific (linear) transformation used to perform predictions. Preliminary tests on the MNIST dataset show that our method can group input instances with regard to their similarity in the internal representation of the neural network.
  arXiv  Detail & Related papers  (2020-02-17T14:16:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.